fix(web): preserve firecrawl crawl + website-policy gate after migration

Two regressions discovered by running the full tests/tools/ suite after
the dispatcher cutover, both fixed in this commit:

1. web_crawl_tool incorrectly errored "search-only" for firecrawl
---------------------------------------------------------------------
The cutover treated any provider with supports_crawl()==False as a
search-only backend and returned the typed search-only error. But
firecrawl can crawl via the legacy multi-page-extract path inside
web_crawl_tool — it just doesn't expose supports_crawl on the plugin
(adding native firecrawl crawl is a clean follow-up).

Fix: only emit the search-only error when the provider supports
NEITHER crawl NOR extract (brave-free / ddgs / searxng). When the
provider supports extract but not crawl (firecrawl), fall through to
the legacy firecrawl-via-extract path below.

2. firecrawl plugin's check_website_access wasn't patchable
---------------------------------------------------------------------
The plugin imported `from tools.website_policy import check_website_access`
INSIDE the extract() function body, so monkeypatching the name on
plugins.web.firecrawl.provider had no effect — the inner import re-bound
the name on every call.

Fix: hoist the import to module level. Cheap (website_policy itself
has no heavy deps) and makes the standard
monkeypatch.setattr(firecrawl_provider, "check_website_access", ...)
pattern work.

Test updates (tests/tools/test_website_policy.py — 4 tests):
  - test_web_extract_short_circuits_blocked_url
  - test_web_extract_blocks_redirected_final_url
    Both: patch the gate at plugins.web.firecrawl.provider (where it
    runs after migration) and force the firecrawl plugin to be the
    active extract provider via FIRECRAWL_API_KEY.
  - test_web_crawl_short_circuits_blocked_url
  - test_web_crawl_blocks_redirected_final_url
    Both: unchanged — the dispatcher-level gate at tools.web_tools.py
    line 1651 still uses the imported `check_website_access` name and
    the firecrawl-fallthrough path is exercised as before.

Verified: 22/22 tests/tools/test_website_policy.py pass.
This commit is contained in:
kshitijk4poor 2026-05-14 00:34:28 +05:30 committed by Teknium
parent b05253ceed
commit 5e54330e27
3 changed files with 39 additions and 23 deletions

View file

@ -350,11 +350,16 @@ def test_browser_navigate_allows_when_shared_file_missing(monkeypatch, tmp_path)
@pytest.mark.asyncio
async def test_web_extract_short_circuits_blocked_url(monkeypatch):
from tools import web_tools
from plugins.web.firecrawl import provider as firecrawl_provider
# Allow test URLs past SSRF check so website policy is what gets tested
monkeypatch.setattr(web_tools, "is_safe_url", lambda url: True)
# The per-URL website-policy gate moved into the firecrawl plugin's
# extract() during the web-provider migration. Patch it at the new
# location; the dispatcher-level gate (used by web_crawl_tool's
# pre-flight) still lives on tools.web_tools.
monkeypatch.setattr(
web_tools,
firecrawl_provider,
"check_website_access",
lambda url: {
"host": "blocked.test",
@ -364,11 +369,13 @@ async def test_web_extract_short_circuits_blocked_url(monkeypatch):
},
)
monkeypatch.setattr(
web_tools,
firecrawl_provider,
"_get_firecrawl_client",
lambda: pytest.fail("firecrawl should not run for blocked URL"),
)
monkeypatch.setattr("tools.interrupt.is_interrupted", lambda: False)
# Force the firecrawl plugin to be the active extract provider.
monkeypatch.setenv("FIRECRAWL_API_KEY", "fake-key")
result = json.loads(await web_tools.web_extract_tool(["https://blocked.test"], use_llm_processing=False))
@ -398,6 +405,7 @@ def test_check_website_access_fails_open_on_malformed_config(tmp_path, monkeypat
@pytest.mark.asyncio
async def test_web_extract_blocks_redirected_final_url(monkeypatch):
from tools import web_tools
from plugins.web.firecrawl import provider as firecrawl_provider
# Allow test URLs past SSRF check so website policy is what gets tested
monkeypatch.setattr(web_tools, "is_safe_url", lambda url: True)
@ -424,9 +432,12 @@ async def test_web_extract_blocks_redirected_final_url(monkeypatch):
},
}
monkeypatch.setattr(web_tools, "check_website_access", fake_check)
monkeypatch.setattr(web_tools, "_get_firecrawl_client", lambda: FakeFirecrawlClient())
# After the web-provider migration, the per-URL gate + firecrawl client
# live in the plugin. Patch both at the plugin location.
monkeypatch.setattr(firecrawl_provider, "check_website_access", fake_check)
monkeypatch.setattr(firecrawl_provider, "_get_firecrawl_client", lambda: FakeFirecrawlClient())
monkeypatch.setattr("tools.interrupt.is_interrupted", lambda: False)
monkeypatch.setenv("FIRECRAWL_API_KEY", "fake-key")
result = json.loads(await web_tools.web_extract_tool(["https://allowed.test"], use_llm_processing=False))